sft-llama3-8b
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:
- Loss: 1.0405
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0608 | 1.0 | 950 | 1.0696 |
| 0.9014 | 2.0 | 1900 | 1.0405 |
| 0.7183 | 3.0 | 2850 | 1.0691 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.3.0
- Datasets 2.14.6
- Tokenizers 0.15.2
- Downloads last month
- 46